Keras
Keras 3 API documentation
KerasCV
Models
Backbones
VGG16 backbones

VGG16 backbones

source

VGG16Backbone class 

keras_cv.models.VGG16Backbone(
    include_rescaling,
    include_top,
    input_tensor=None,
    num_classes=None,
    input_shape=(224, 224, 3),
    pooling=None,
    classifier_activation="softmax",
    name="VGG16",
    **kwargs
)

Reference:

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • include_top: bool, whether to include the 3 fully-connected layers at the top of the network. If provided, num_classes must be provided.
  • num_classes: int, optional number of classes to classify images into, only to be specified if include_top is True.
  • input_shape: tuple, optional shape tuple, defaults to (224, 224, 3).
  • input_tensor: Tensor, optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • pooling: bool, Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional block.
    • avg means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classifier_activation:str or callable. The activation function to use on the “top” layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the “top” layer. When loading pretrained weights, classifier_activation can only be None or "softmax".
  • name: (Optional) name to pass to the model, defaults to “VGG16”.

Returns

A keras.Model instance.

source

from_preset method 

VGG16Backbone.from_preset()

Not implemented.

No presets available for this class.